Home/Pricing/RTX 4090 Instance

RTX 4090 Instance

A dedicated RTX 4090 for inference, LoRA fine-tuning, and development work.

Compute Plans billed per month

A single-tenant NVIDIA RTX 4090 instance with root access to the full CUDA stack. Ideal for serving 7B-class models, running LoRA fine-tunes, or as a development box that does not share silicon with anyone else. Provisioned within one business day of payment confirmation.

What is included

  • Dedicated NVIDIA RTX 4090 (24 GB)
  • 16 vCPU · 64 GB RAM · 1 TB NVMe
  • Root access — any CUDA stack
  • 99.9% uptime SLA
  • Cancel or resize with 30-day notice

Specification

GPU
NVIDIA RTX 4090
VRAM
24 GB GDDR6X
CPU
16 vCPU
Memory
64 GB
Storage
1 TB NVMe

Other Compute Plans

A100 Node $899.00

Production-grade A100 capacity for fine-tuning and batch inference.
H100 Node $1,499.00

Flagship Hopper performance for frontier training and low-latency serving.
H100 8-GPU Cluster $9,999.00

An 8×H100 NVLink cluster for distributed training at scale.

Start routing in minutes

One endpoint. Every frontier model.

Create an account, pick a plan, and point your existing OpenAI client at our base URL. No SDK rewrite, no lock-in.

Browse plans Talk to sales